article · Neural Computing and Applications
Gestational diabetes mellitus creates notable risks for both mothers and infants, usually receiving diagnosis between 22 and 26 weeks of gestation. Continuous maternal monitoring allows for earlier detection and intervention. A three-tier architecture combines Internet of Things sensors, fog computing nodes, and cloud storage to monitor pregnant patients. Invasive and non-invasive sensors gather vital signs, which are transmitted to fog computing nodes before long-term storage in the cloud. Within the fog layer, an automated caching mechanism replaces unused data to maintain storage efficiency, while a deep neural network predicts the onset of gestational diabetes in the second trimester. Evaluated on clinical records from over sixteen thousand pregnant patients in an intensive care dataset, the system achieved a prediction accuracy of 0.957 and an area under the curve of 0.942. Model transparency is supported through local and global explainability tools.
Gestational diabetes is typically diagnosed late in the second trimester, leaving limited time to prevent complications for mother and child. Continuous health tracking coupled with explainable artificial intelligence enables earlier risk detection. Using fog computing to process sensor readings locally reduces network congestion and data storage costs, creating a practical pathway for continuous, understandable maternal health assessment during pregnancy.
The framework could support remote maternal care platforms, clinical decision-support tools, and connected medical device ecosystems in healthcare organisations. Intended users include obstetricians, clinical monitoring teams, and healthcare software developers. Evaluated retrospectively on the MIMIC III benchmark dataset, the technology sits at an applied, proof-of-concept stage and requires real-time prospective testing with physical sensors in clinical settings before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Gestational diabetes mellitus (GDM) is one of the pregnancy complications that poses a significant risk on mothers and babies as well. GDM usually diagnosed at 22–26 of gestation. However, the early prediction is desirable as it may contribute to decrease the risk. The continuous monitoring for mother’s vital signs helps in predicting any deterioration during pregnancy. The originality of this paper is to provide comprehensive framework for pregnancy women monitoring. The proposed Data Replacement and Prediction Framework consists of three layers which are: (i) IoT Layer, (ii) Fog Layer, and (iii) Cloud Layer. The first layer used IOT sensors to aggregate vital sings from pregnancies using invasive and noninvasive sensors. Then the vital signs transmitted to fog nodes to processed and finally stored in the cloud layer. The main contribution in this paper is located in the fog layer producing GDM module to implement two influential tasks which are: (i) Data Finding Methodology (DFM), and (ii) Explainable Prediction Algorithm (EPM) using DNN. First, the DFM is used to replace the unused data to free the cache space for the new incoming data items. The cache replacement is very important in the case of healthcare system as the incoming vital signs are frequent and must be replaced continuously. Second, the EPM is used to predict the incidence of GDM that may occur in the second trimester of the pregnancy. To evaluate our model, we extract data of 16,354 pregnancy women from medical information mart for intensive care (MIMIC III) benchmark dataset. For each woman, vital signs, demographic data and laboratory tests was aggregated. The results of the prediction model superior the state of the art (ACC = 0.957, AUC = 0.942). Regarding to explainability, we utilized Shapley additive explanation framework to provide local and global explanation for the developed models. Overall, the proposed framework is medically intuitive, allow the early prediction of GDM with cost effective solution .
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-022-08007-5
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
